David William Pearson

Applications of artificial neural networks

In this article we consider some theoretical aspects of neural networks and some of their varied applications. The theoretical aspects are presented from the point of view of a system, basically input/state/output. For the applications, we consider large systems: from production systems, through biological and chemical systems and on to environmental systems.

Web Information Retrieval Based on User Profile

With the growing popularity of the World Wide Web, the amount of available information is so great that finding the right and useful information becomes a very hard task for an end user. In this paper, we propose a new approach for personal Web information retrieval. The originality of our approach is a choice of indexing terms depending on the user request but also on his profile. The general idea is to consider that the need of a user depends on his request but also on his knowledge acquired through time on the thematic of his request.

Information retrieval model based on user profile

With the development of internet and storage devices, online document servers abound with enormous quantities of documents, so that finding the right and useful information becomes a very difficult task. The end user, generally overloaded by information, can’t efficiently perceive such information. It became urgent to propose new information retrieval systems able to apprehend efficiently these enormous quantities of documents. In this paper we present PQIR an information retrieval model based on user profile. The originality of our approach is a choice of indexing terms depending on the user request but also on his profile. An empirical study confirms the relevance of our approach.

A Fuzzy Approach to Sociodynamical Interactions

In this paper we present a sociodynamical model of a network of people and their attitudes towards each other. The model is based on concepts from fuzzy logic. The dynamic element of the model allows us to simulate the temporal evolution of the attitudes and to see how this evolution might converge to a stable state.

LUCI: A Personalization Documentary System Based on the Analysis of the History of the User's Actions

With the development of Internet and storage devices, online document servers abound with enormous quantities of documents from various themes. The online search of pertinent documents is a fastidious task and ”search engine” may overcome this difficulty. However, in such engines, each new document need must be formulated by a new request. Recently, new approaches were proposed to solve this problem by taking into account the user profile. However, these approaches don’t consider the evolution in time of the document classes consulted by the user. In this paper, we propose a new approach for learning the user long-term profile for textual document filtering. In this framework, the documents consulted by the user are classified in a dynamic way, then we analyze the distribution in the time of the document classes. The approach aim is to determine, as well as possible, the document classes which interest the user. We also propose a system called LUCI, which allows an online document’s personalization by using this approach. An empirical study confirms the relevance of our approach.

Vertical Vector Fields and Neural Networks: An Application in Atmospheric Pollution Forecasting

In this paper we look at the role that vertical fields can play in enhancing the performance of a feedforward neural network. Vertical fields help us to determine zones in the input space that are mapped onto the same output, they act in a similar way to kernels of linear mappings but in a nonlinear setting. In the paper we illustrate our ideas using data from a real application, namely forecasting atmospheric pollution for the town of Saint-Etienne in France.

Social Agents in Dynamic Equilibrium

A simple model for social group interactions is introduced. The model is investigated for the minimal group size for the model N=3. Examples of model of model behaviour in terms of dynamic and static equilibrium are presented. Directions for further study of the model are considered.

String distances and uniformities

The Levenstein or edit distance was developed as a metric for calculating distances between character strings.We are looking at weighting the different edit operations (insertion, deletion, substitution) to obtain different types of classifications of sets of strings. As a more general and less constrained approach we introduce topological notions and in particular uniformities.

Dynamic Data Probes

In this paper we look at a dynamic method for analysing data, called a data probe. The probe flies through the data space and is affected by the proximity and number of data points. The trajectory followed by the probe provides information about how the data are organised geometrically. We apply a state feedback method to the probe equations to make the probe search out certain data values.

Data Probes, Vertical Trajectories and Classification: A Tentative Study

Data Probes, Vertical Trajectories and Classification: A Tentative Study In this paper we introduce a method of classification based on data probes. Data points are considered as point masses in space and a probe is simply a particle that is launched into the space. As the probe passes by data clusters, its trajectory will be influenced by the point masses. We use this information to help us to find vertical trajectories. These are trajectories in the input space that are mapped onto the same value in the output space and correspond to the data classes.